> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryprofound.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Get Answers
The raw per-execution rows behind every report: one row per model response,
with its mentions, citations, and search queries. No aggregation.
* **No `group_by` / `sort`:** rows are newest-first by date.
* **`include`** picks which fields to return (`response`, `mentions`, `citations`, `search_queries`, …); omit it for all.
* `mentions` is a flat, deduped list in the order entities appear in the response.
* **Filters:** prompt-level fields plus `analysis_type` (prompt-level: `visibility`·`sentiment`·`factcheck`), and top-level `domain`/`page` leaves: `is` one value or `in` a list (exact cited-URL match).
New to the v2 reports? See [Filtering & concepts](/rest-api/reports/reports-v2-overview) for the shared request shape, filter tree, grouping, and pagination.
`POST /v2/prompts/answers/stream` takes the **same request body** and
returns [Server-Sent Events](https://developer.mozilla.org/docs/Web/API/Server-sent_events):
one `summary` event (the `info` block), then one `result` event per row.
`limit`/`cursor` are ignored; it returns everything by default. Pass
`max_results` to cap.
```text Response (text/event-stream) theme={null}
event: summary
data: { ...the info block... }
event: result ← one per row, same shape as data[] above
data: {"date": "2026-06-19", "model": {"name": "ChatGPT"}, "prompt": "", "mentions": ["Profound", ""], "citations": ["https://example.com/article"]}
```
```bash cURL theme={null}
curl -X POST https://api.tryprofound.com/v2/prompts/answers \
-H "X-API-Key: " \
-H "Content-Type: application/json" \
-d '{
"category_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
"start_date": "2026-06-18",
"end_date": "2026-06-19",
"limit": 10
}'
```
```json 200 theme={null}
{
"info": {
"total_results": 27690,
"count": 10,
"next_cursor": "Z0FBQUFBQnFQcjNsbDZZaWlzZjR2cXJt...",
"models": ["ChatGPT", "Google Gemini", "Perplexity", "Claude", "..."],
"include": [
"run_id", "date", "model", "topic", "topic_id", "persona", "region",
"tags", "prompt", "prompt_id", "response", "mentions", "citations",
"search_queries", "analysis_types"
],
"start_date": "2026-06-18",
"end_date": "2026-06-19",
"filter": null
},
"data": [
{
"run_id": "",
"date": "2026-06-19",
"model": { "id": "", "name": "ChatGPT" },
"topic": "",
"topic_id": "",
"region": "United States",
"persona": null,
"tags": [],
"prompt": "",
"prompt_id": "",
"response": "",
"mentions": ["Profound", ""],
"citations": ["https://example.com/article"],
"search_queries": [""],
"analysis_types": ["visibility"]
}
// ...9 more rows (count: 10, total_results: 27690); paginate with next_cursor
]
}
```
## OpenAPI
````yaml POST /v2/prompts/answers
openapi: 3.1.0
info:
title: External API
version: 6c43b49565a0c4e7cb023e22242cc3df28ee7153
servers:
- url: https://api.tryprofound.com
description: Production Server
security: []
paths:
/v2/prompts/answers:
post:
tags:
- Prompts
summary: Query Answers V2
operationId: query_answers_v2_v2_prompts_answers_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/AnswersV2Query'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
additionalProperties: true
type: object
title: Response Query Answers V2 V2 Prompts Answers Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- APIKeyHeader: []
- BearerAuth: []
x-codeSamples:
- lang: JavaScript
source: |-
import Profound from '@profoundai/client';
const client = new Profound({
apiKey: process.env['PROFOUND_API_KEY'], // This is the default and can be omitted
});
const response = await client.prompts.answersV2({
category_id: 'category_id',
end_date: 'end_date',
start_date: 'start_date',
});
console.log(response);
- lang: Python
source: |-
import os
from profound import Profound
client = Profound(
api_key=os.environ.get("PROFOUND_API_KEY"), # This is the default and can be omitted
)
response = client.prompts.answers_v2(
category_id="category_id",
end_date="end_date",
start_date="start_date",
)
print(response)
components:
schemas:
AnswersV2Query:
properties:
category_id:
type: string
title: Category Id
start_date:
type: string
title: Start Date
description: YYYY-MM-DD, ET, inclusive
end_date:
type: string
title: End Date
description: YYYY-MM-DD, ET, inclusive
include:
anyOf:
- items:
type: string
enum:
- run_id
- date
- model
- topic
- topic_id
- persona
- region
- tags
- prompt
- prompt_id
- response
- mentions
- citations
- search_queries
- analysis_types
- sentiment_claims
type: array
- type: 'null'
title: Include
description: >-
Which row fields to return: `run_id`, `date`, `model`, `topic`,
`topic_id`, `region`, `persona`, `tags`, `prompt`, `prompt_id`,
`response`, `mentions`, `citations`, `search_queries`,
`analysis_types`, `sentiment_claims`. Omit for all of them.
filter:
anyOf:
- $ref: '#/components/schemas/FilterNode'
- type: 'null'
description: >-
and/or/not tree over `model`, `topic`, `region`, `persona`,
`prompt`, `tag`, `analysis_type` (visibility/sentiment/factcheck);
plus top-level `and` leaves `domain` or `page` (`is` one value, or
`in` a list). Substring-search the prompt with `{"field": "prompt",
"op": "contains", "value": "…"}`.
limit:
anyOf:
- type: integer
maximum: 50
exclusiveMinimum: 0
- type: 'null'
title: Limit
description: Page size; default 10, max 50.
max_results:
anyOf:
- type: integer
exclusiveMinimum: 0
- type: 'null'
title: Max Results
description: >-
Stream endpoint only: cap the number of streamed rows (default:
all).
cursor:
anyOf:
- type: string
- type: 'null'
title: Cursor
additionalProperties: false
type: object
required:
- category_id
- start_date
- end_date
title: AnswersV2Query
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
FilterNode:
properties:
and:
anyOf:
- items:
$ref: '#/components/schemas/FilterNode'
type: array
- type: 'null'
title: And
or:
anyOf:
- items:
$ref: '#/components/schemas/FilterNode'
type: array
- type: 'null'
title: Or
not:
anyOf:
- $ref: '#/components/schemas/FilterNode'
- type: 'null'
field:
anyOf:
- type: string
- type: 'null'
title: Field
op:
anyOf:
- type: string
- type: 'null'
title: Op
value:
title: Value
additionalProperties: false
type: object
title: FilterNode
description: A leaf (`field`/`op`/`value`) or an `and`/`or`/`not` group.
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
APIKeyHeader:
type: apiKey
in: header
name: X-API-Key
BearerAuth:
type: http
scheme: bearer
````